Simulating daily PM2.5 concentrations using wavelet analysis and artificial neural network with remote sensing and surface observation data

Chemosphere, Journal Year: 2023, Volume and Issue: 340, P. 139886 - 139886

Published: Aug. 21, 2023

Language: Английский

---

AnnoPRO: a strategy for protein function annotation based on multi-scale protein representation and a hybrid deep learning of dual-path encoding

Genome biology, Journal Year: 2024, Volume and Issue: 25(1)

Published: Feb. 1, 2024

Abstract Protein function annotation has been one of the longstanding issues in biological sciences, and various computational methods have developed. However, existing suffer from a serious long-tail problem, with large number GO families containing few annotated proteins. Herein, an innovative strategy named AnnoPRO was therefore constructed by enabling sequence-based multi-scale protein representation, dual-path encoding using pre-training, long short-term memory-based decoding. A variety case studies based on different benchmarks were conducted, which confirmed superior performance among available methods. Source code models made freely at: https://github.com/idrblab/AnnoPRO https://zenodo.org/records/10012272

Language: Английский

---

Comparative Analysis of Multiple Deep Learning Models for Forecasting Monthly Ambient PM2.5 Concentrations: A Case Study in Dezhou City, China

Atmosphere, Journal Year: 2024, Volume and Issue: 15(12), P. 1432 - 1432

Published: Nov. 28, 2024

Ambient air pollution affects human health, vegetative growth and sustainable socio-economic development. Therefore, data in Dezhou City China are collected from January 2014 to December 2023, multiple deep learning models used forecast PM2.5 concentrations. The ability of the is evaluated compared with observed using various statistical parameters. Although all eight can accomplish forecasting assignments, precision accuracy CNN-GRU-LSTM method 34.28% higher than that ANN method. result shows has best performance other seven models, achieving an R (correlation coefficient) 0.9686 RMSE (root mean square error) 4.6491 μg/m3. values CNN, GRU LSTM 57.00%, 35.98% 32.78% method, respectively. results reveal predictor remarkably improves performances benchmark overall forecasting. This research provides a new perspective for predictive ambient model provide scientific basis prevention control.

Language: Английский

---

Assessing the effectiveness of long short-term memory and artificial neural network in predicting daily ozone concentrations in Liaocheng City

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 25, 2025

Ozone pollution affects food production, human health, and the lives of individuals. Due to rapid industrialization urbanization, Liaocheng has experienced increasing ozone concentration over several years. Therefore, become a major environmental problem in City. Long short-term memory (LSTM) artificial neural network (ANN) models are established predict concentrations City from 2014 2023. The results show general improvement accuracy LSTM model compared ANN model. Compared ANN, an increase determination coefficient (R2), value 0.6779 0.6939, decrease root mean square error (RMSE) 27.9895 μg/m3 27.2140 absolute (MAE) 21.6919 20.8825 μg/m3. prediction is superior terms R, RMSE, MAE. In summary, promising technique for predicting concentrations. Moreover, by leveraging historical data enables accurate predictions future on global scale. This will open up new avenues controlling mitigating pollution.

Language: Английский

---

Air-quality prediction based on the ARIMA-CNN-LSTM combination model optimized by dung beetle optimizer

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: July 26, 2023

Abstract Air pollution is a serious problem that affects economic development and people’s health, so an efficient accurate air quality prediction model would help to manage the problem. In this paper, we build combined accurately predict AQI based on real data from four cities. First, use ARIMA fit linear part of CNN-LSTM non-linear avoid blinding in hyperparameter setting. Then, dilemma setting, Dung Beetle Optimizer algorithm find hyperparameters model, determine optimal hyperparameters, check accuracy model. Finally, compare proposed with nine other widely used models. The experimental results show paper outperforms comparison models terms root mean square error (RMSE), absolute (MAE) coefficient determination (R 2 ). RMSE values for cities were 7.594, 14.94, 7.841 5.496; MAE 5.285, 10.839, 5.12 3.77; R 0.989, 0.962, 0.953 respectively.

Language: Английский

---

Prediction of monthly average and extreme atmospheric temperatures in Zhengzhou based on artificial neural network and deep learning models

Frontiers in Forests and Global Change, Journal Year: 2023, Volume and Issue: 6

Published: Dec. 8, 2023

Introduction Atmospheric temperature affects the growth and development of plants has an important impact on sustainable forest ecological systems. Predicting atmospheric is crucial for management planning. Methods Artificial neural network (ANN) deep learning models such as gate recurrent unit (GRU), long short-term memory (LSTM), convolutional (CNN), CNN-GRU, CNN-LSTM, were utilized to predict change monthly average extreme temperatures in Zhengzhou City. Average data from 1951 2022 divided into training sets (1951–2000) prediction (2001–2022), 22 months used model input next month. Results Discussion The number neurons hidden layer was 14. Six different algorithms, along with 13 various functions, trained compared. ANN evaluated terms correlation coefficient (R), root mean square error (RMSE), absolute (MAE), good results obtained. Bayesian regularization (trainbr) best performing algorithm predicting average, minimum maximum compared other algorithms R (0.9952, 0.9899, 0.9721), showed lowest values RMSE (0.9432, 1.4034, 2.0505), MAE (0.7204, 1.0787, 1.6224). CNN-LSTM performance. This method had generalization ability could be forecast areas. Future climate changes projected using model. temperature, 2030 predicted 17.23 °C, −5.06 42.44 whereas those 2040 17.36 −3.74 42.68 respectively. These suggest that continue warming future.

Language: Английский

---

Deep learning coupled model based on TCN-LSTM for particulate matter concentration prediction

Atmospheric Pollution Research, Journal Year: 2023, Volume and Issue: 14(4), P. 101703 - 101703

Published: March 4, 2023

Language: Английский

---

Real time image-based air quality forecasts using a 3D-CNN approach with an attention mechanism

Chemosphere, Journal Year: 2023, Volume and Issue: 333, P. 138867 - 138867

Published: May 6, 2023

Language: Английский

---

Time series prediction model using LSTM-Transformer neural network for mine water inflow

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 7, 2024

Mine flooding accidents have occurred frequently in recent years, and the predicting of mine water inflow is one most crucial flood warning indicators. Further, characterized by non-linearity instability, making it difficult to predict. Accordingly, we propose a time series prediction model based on fusion Transformer algorithm, which relies self-attention, LSTM captures long-term dependencies. In this paper, Baotailong Heilongjiang Province used as sample data, data divided into different ratios training set test order obtain optimal results. study, demonstrate that LSTM-Transformer exhibits highest accuracy when ratio 7:3. To improve efficiency search, combination random search Bayesian optimization determine network parameters regularization parameters. Finally, verify model, compared with LSTM, CNN, CNN-LSTM models. The results prove has accuracy, all indicators its are well improved.

Language: Английский

---

Comparative Analysis of Convolutional Neural Network-Long Short-Term Memory, Sparrow Search Algorithm-Backpropagation Neural Network, and Particle Swarm Optimization-Extreme Learning Machine Models for the Water Discharge of the Buzău River, Romania

Water, Journal Year: 2024, Volume and Issue: 16(2), P. 289 - 289

Published: Jan. 15, 2024

Modeling and forecasting the river flow is essential for management of water resources. In this study, we conduct a comprehensive comparative analysis different models built monthly discharge Buzău River (Romania), measured in upper part river’s basin from January 1955 to December 2010. They employ convolutional neural networks (CNNs) coupled with long short-term memory (LSTM) networks, named CNN-LSTM, sparrow search algorithm backpropagation (SSA-BP), particle swarm optimization extreme learning machines (PSO-ELM). These are evaluated based on various criteria, including computational efficiency, predictive accuracy, adaptability training sets. The obtained applying CNN-LSTM stand out as top performers, demonstrating superior efficiency high especially when set containing data series 1984 (putting Siriu Dam operation) September 2006 (Model type S2). This research provides valuable guidance selecting assessing prediction models, offering practical insights scientific community real-world applications. findings suggest that Model S2 preferred choice forecast predictions due its speed accuracy. S (considering recorded 2006) recommended secondary option. S1 (with period 1955–December 1983) suitable other unavailable. study advances field by presenting precise these their respective strengths

Language: Английский

---